{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/black-box-generation-of-adversarial-text","title":"Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers","arxiv_id":"1801.04354","date":"2018-01-13","proceeding":null,"authors":["Ji Gao","Jack Lanchantin","Mary Lou Soffa","Yanjun Qi"],"abstract":"Although various techniques have been proposed to generate adversarial\nsamples for white-box attacks on text, little attention has been paid to\nblack-box attacks, which are more realistic scenarios. In this paper, we\npresent a novel algorithm, DeepWordBug, to effectively generate small text\nperturbations in a black-box setting that forces a deep-learning classifier to\nmisclassify a text input. We employ novel scoring strategies to identify the\ncritical tokens that, if modified, cause the classifier to make an incorrect\nprediction. Simple character-level transformations are applied to the\nhighest-ranked tokens in order to minimize the edit distance of the\nperturbation, yet change the original classification. We evaluated DeepWordBug\non eight real-world text datasets, including text classification, sentiment\nanalysis, and spam detection. We compare the result of DeepWordBug with two\nbaselines: Random (Black-box) and Gradient (White-box). Our experimental\nresults indicate that DeepWordBug reduces the prediction accuracy of current\nstate-of-the-art deep-learning models, including a decrease of 68\\% on average\nfor a Word-LSTM model and 48\\% on average for a Char-CNN model.","url_abs":"http://arxiv.org/abs/1801.04354v5","url_pdf":"http://arxiv.org/pdf/1801.04354v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"black-box-generation-of-adversarial-text","repo_url":"https://github.com/QData/deepWordBug","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"black-box-generation-of-adversarial-text","repo_url":"https://github.com/alankarj/robust_nlp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"adversarial-text","task_name":"Adversarial Text"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"spam-detection","task_name":"Spam detection"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":null,"task_name":"Text Classification (Sentiment Analysis)"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.04354","atlas_url":"https://app.syntology.ai/?focus=1801.04354","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.04354"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/QData/deepWordBug","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alankarj/robust_nlp","reach":{"status":"ok"}}],"summary":{"ran_violates":1,"ran_honours":2},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"99c60461bf25d487","entry":"recoveradv","repo":"QData/deepWordBug","repo_kind":"official","path":"attack_interactive.py","file_url":"https://github.com/QData/deepWordBug/blob/HEAD/attack_interactive.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"99c60461bf25d487"}},{"code_sha256_prefix":"c7e51df2685092e8","entry":"simple_tokenize","repo":"QData/deepWordBug","repo_kind":"official","path":"attack_interactive.py","file_url":"https://github.com/QData/deepWordBug/blob/HEAD/attack_interactive.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c7e51df2685092e8"}},{"code_sha256_prefix":"0143f1e7af88390c","entry":"transchar","repo":"QData/deepWordBug","repo_kind":"official","path":"attack_interactive.py","file_url":"https://github.com/QData/deepWordBug/blob/HEAD/attack_interactive.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0143f1e7af88390c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}